Ultrabitch/mcp-dexscreener

🚀 DexScreener MCP Server

A Model Context Protocol (MCP) server that provides access to the DexScreener API with Telegram-optimized formatting and automatic chain detection.

✨ Features

• 🔍 Auto-detect blockchain from token address format
• 📱 Telegram-optimized formatting with market cap prioritization
• 🐳 Docker-ready for headless deployment
• ⚡ High-performance with negligible address detection overhead
• 🔗 Multi-chain support (Solana, Ethereum, BSC, Polygon, Arbitrum, Base)
• 📊 Real-time market data from DexScreener API

🚀 Quick Start

Option 1: Docker (Recommended for Production)

# Clone and run
git clone <your-repo-url>
cd mcp-dexscreener
docker-compose up -d

# Server available at http://localhost:3001

Option 2: Local Development

# Install dependencies
npm install

# Run STDIO version (for Claude Desktop)
npm start

# Run SSE version (for remote agents)
node index-sse.js

📡 API Endpoints

🛠️ Available Tools

🆕 getTokenInfo (Auto-Detection)

Get token information with automatic chain detection:

getTokenInfo({ 
  tokenAddress: "DtR4D9FtVoTX2569gaL837ZgrB6wNjj6tkmnX9Rdk9B2" 
})
// Automatically detects Solana and returns formatted data

Traditional Tools (Require Chain ID)

• getPairsByToken - Get pairs by token address
• searchPairs - Search pairs by query
• getPairByChainAndAddress - Get specific pair data
• getTokenPools - Get token pools
• getLatestTokenProfiles - Latest token profiles
• checkTokenOrders - Check token orders

📱 Telegram Format Example

🚀 **LAUNCHCOIN** [+15.77%]

🔗 Solana @ Raydium

**MC: $225.9M**
USD: $0.2258

**FDV:** $225.9M  |  **Liq:** $1.9M
**Vol 24h:** $16.5M  |  **Txns:** 62.6K

CA: `Ey59PH7Z4BFU4HjyKnyMdWt5GGN76KazTAwQihoUXRnk`

📊 [Chart](link) | 🌐 [Website](link) | 🐦 [Twitter](link)

🔗 Chain Detection

The server automatically detects blockchain from address format:

🐳 Docker Deployment

Production Setup

# Build and run
docker-compose up -d

# Test container health (optional)
node test-docker.js

# View logs
docker-compose logs -f

# Stop
docker-compose down

Configuration

The Docker setup includes:

• ✅ Production-optimized Node.js Alpine image
• ✅ Simplified deployment (no non-root user complications)
• ✅ Health checks and auto-restart
• ✅ Resource limits (512MB RAM, 0.5 CPU)
• ✅ Structured logging with rotation
• ✅ Comprehensive test suite for container health

🖥️ Agent Integration

For Remote Agents/Orchestrators

const mcpClient = new MCPClient({
  sseUrl: "http://your-server:3001/sse",
  messagesUrl: "http://your-server:3001/messages"
});

// Use the auto-detection tool
const result = await mcpClient.callTool("getTokenInfo", {
  tokenAddress: "DtR4D9FtVoTX2569gaL837ZgrB6wNjj6tkmnX9Rdk9B2"
});

For Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "dexscreener": {
      "command": "node",
      "args": ["/absolute/path/to/index.js"]
    }
  }
}

Config file locations:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

⚡ Performance

• Address Detection: ~0.001ms (single regex match)
• EVM Fallback: ~200-500ms max (only on API failure)
• Rate Limits: 60/min for profiles, 300/min for pairs/search

🔧 Development

Project Structure

mcp-dexscreener/
├── index.js          # STDIO transport (Claude Desktop)
├── index-sse.js      # HTTP/SSE transport (remote agents)
├── package.json      # Dependencies and scripts
├── Dockerfile        # Production container
├── docker-compose.yml # Orchestration
├── test-docker.js    # Container health test suite
└── CLAUDE.md         # Development notes (gitignored)

Testing

The project includes a comprehensive test suite for Docker deployments:

# Run container health tests
node test-docker.js

Tests verify:

• ✅ Health endpoint functionality
• ✅ API information endpoint
• ✅ SSE connection handling
• ✅ MCP endpoint protection
• ✅ Proper error responses

Environment Variables

• PORT - Server port (default: 3001)
• NODE_ENV - Environment (production/development)

📄 API Reference

Based on DexScreener API Documentation

Rate limits:

• Token profiles/boosts: 60 requests/minute
• Pairs/search: 300 requests/minute

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test with Docker: docker-compose up --build
5. Submit a pull request

📜 License

MIT License - see LICENSE file for details

🆘 Support

• 📖 MCP Documentation
• 🔗 DexScreener API Docs
• 🐛 Report Issues

Built with ❤️ for the crypto community